CLCC (Chinese Linguistics & Cognition Challenge) is a Chinese evaluation dataset from the FlagEval team at BAAI (Beijing Academy of Artificial Intelligence), which its results are judged by an judge model. This judge model, FlagJudge, is based on Llama-33B and trained on the CLCC dataset with 40,000 manually labeled examples.
CLCC (Chinese Linguistics & Cognition Challenge) is a Chinese evaluation dataset from the FlagEval team at BAAI (Beijing Academy of Artificial Intelligence), which its results are judged by an judge model. This judge model, FlagJudge, is based on Llama-33B and trained on the CLCC dataset with 40,000 manually labeled examples.